Beatriz Marcotegui

Segmentation-based video coding system allowing the manipulation of objects

This paper presents a generic video coding algorithm allowing the content-based manipulation of objects. This manipulation is possible thanks to the definition of a spatiotemporal segmentation of the sequences. The coding strategy relies on a joint optimization in the rate-distortion sense of the partition definition and of the coding techniques to be used within each region. This optimization creates the link between the analysis and synthesis parts of the coder. The analysis defines the time evolution of the partition, as well as the elimination or the appearance of regions that are homogeneous either spatially or in motion. The coding of the texture as well as of the partition relies on region-based motion compensation techniques. The algorithm offers a good compromise between the ability to track and manipulate objects and the coding efficiency.

Exudate detection in color retinal images for mass screening of diabetic retinopathy

The automatic detection of exudates in color eye fundus images is an important task in applications such as diabetic retinopathy screening. The presented work has been undertaken in the framework of the TeleOphta project, whose main objective is to automatically detect normal exams in a tele-ophthalmology network, thus reducing the burden on the readers. A new clinical database, e-ophtha EX, containing precisely manually contoured exudates, is introduced. As opposed to previously available databases, e-ophtha EX is very heterogeneous. It contains images gathered within the OPHDIAT telemedicine network for diabetic retinopathy screening. Image definition, quality, as well as patients condition or the retinograph used for the acquisition, for example, are subject to important changes between different examinations. The proposed exudate detection method has been designed for this complex situation. We propose new preprocessing methods, which perform not only normalization and denoising tasks, but also detect reflections and artifacts in the image. A new candidates segmentation method, based on mathematical morphology, is proposed. These candidates are characterized using classical features, but also novel contextual features. Finally, a random forest algorithm is used to detect the exudates among the candidates. The method has been validated on the e-ophtha EX database, obtaining an AUC of 0.95. It has been also validated on other databases, obtaining an AUC between 0.93 and 0.95, outperforming state-of-the-art methods.

FAST IMPLEMENTATION OF WATERFALL BASED ON GRAPHS

The waterfall algorithm is a contrast-based hierarchical segmentation approach. In this paper we propose an efficient implementation based on the minimum spanning tree of the neighborhood graph. Furthermore, other hierarchies are proposed and compared to the original version of the algorithm.

A video object generation tool allowing friendly user interaction

In this paper we describe an interactive video object segmentation tool developed in the framework of the ACTS-AC098 MOMUSYS project. The Video Object Generator with User Environment (VOGUE) combines three different sets of automatic and semi-automatic-tool (spatial segmentation, object tracking and temporal segmentation) with general purpose tools for user interaction. The result is an integrated environment allowing the user-assisted segmentation of any sort of video sequences in a friendly and efficient manner.

Text segmentation in natural scenes using Toggle-Mapping

We offer, in this paper, a new method to segment text in natural scenes. This method is based on the use of a morphological operator: the Toggle Mapping. The efficiency of the method is illustrated and the method is compared, according to various criteria, with common methods issued from the state of the art. This comparison shows that our method gives better results and is faster than the state of the art methods. Our method reduces also the number of segmented regions. This can lead to time saving in a complete scheme (executing time of multiple processing steps usually depends on the number of regions) and proves that our algorithm is more relevant.

Point cloud segmentation towards urban ground modeling

This paper presents a new method for segmentation and interpretation of 3D point clouds from mobile LIDAR data. The main contribution of this work is the automatic detection and classification of artifacts located at the ground level. The detection is based on Top-Hat of hole filling algorithm of range images. Then, several features are extracted from the detected connected components (CCs). Afterward, a stepwise forward variable selection by using Wilks Lambda criterion is performed. Finally, CCs are classified in four categories (lampposts, pedestrians, cars, the others) by using a SVM machine learning method.

A toolbox for interactive segmentation based on nested partitions

This paper presents a toolbox for interactive image segmentation based on a series of nested partitions of increasing coarseness. The user can navigate among the different resolution levels and select regions with simple mouse clicks. The whole family of partitions can be created during a single morphological flooding of the image, leading to a very fast algorithm. The information is stored in a minimum spanning tree.

Snoopertext: A multiresolution system for text detection in complex visual scenes

Text detection in natural images remains a very challenging task. For instance, in an urban context, the detection is very difficult due to large variations in terms of shape, size, color, orientation, and the image may be blurred or have irregular illumination, etc. In this paper, we describe a robust and accurate multiresolution approach to detect and classify text regions in such scenarios. Based on generation/validation paradigm, we first segment images to detect character regions with a multiresolution algorithm able to manage large character size variations. The segmented regions are then filtered out using shapebased classification, and neighboring characters are merged to generate text hypotheses. A validation step computes a region signature based on texture analysis to reject false positives. We evaluate our algorithm in two challenging databases, achieving very good results.

Text detection in street level images

Text detection system for natural images is a very challenging task in Computer Vision. Image acquisition introduces distortion in terms of perspective, blurring, illumination, and characters which may have very different shape, size, and color. We introduce in this article a full text detection scheme. Our architecture is based on a new process to combine a hypothesis generation step to get potential boxes of text and a hypothesis validation step to filter false detections. The hypothesis generation process relies on a new efficient segmentation method based on a morphological operator. Regions are then filtered and classified using shape descriptors based on Fourier, Pseudo Zernike moments and an original polar descriptor, which is invariant to rotation. Classification process relies on three SVM classifiers combined in a late fusion scheme. Detected characters are finally grouped to generate our text box hypotheses. Validation step is based on a global SVM classification of the box content using dedicated descriptors adapted from the HOG approach. Results on the well-known ICDAR database are reported showing that our method is competitive. Evaluation protocol and metrics are deeply discussed and results on a very challenging street-level database are also proposed.

TerraMobilita/iQmulus urban point cloud analysis benchmark

The objective of the TerraMobilita/iQmulus 3D urban analysis benchmark is to evaluate the current state of the art in urban scene analysis from mobile laser scanning (MLS) at large scale. A very detailed semantic tree for urban scenes is proposed. We call analysis the capacity of a method to separate the points of the scene into these categories (classification), and to separate the different objects of the same type for object classes (detection). A very large ground truth is produced manually in two steps using advanced editing tools developed especially for this benchmark. Based on this ground truth, the benchmark aims at evaluating the classification, detection and segmentation quality of the submitted results. Graphical abstractDisplay Omitted HighlightsVery rich data: high accuracy, high resolution, many attributes.Massive data: 160 million annotated points thanks to a performant web based annotation tool (and many hours of work).Rich semantics organized in a semantic tree with various levels of generalization.Very objective evaluation metrics.